!pip install folium branca
import folium
from folium.plugins import HeatMap
import matplotlib.pyplot as plt
import plotly.express as px
import numpy as np
import pandas as pd
import warnings 
import termcolor
import plotly.io as pio
pio.renderers.default = 'notebook_connected'

warnings.filterwarnings('ignore')
print('libraries installed!')

Requirement already satisfied: folium in /opt/anaconda3/lib/python3.12/site-packages (0.18.0)
Requirement already satisfied: branca in /opt/anaconda3/lib/python3.12/site-packages (0.8.0)
Requirement already satisfied: jinja2>=2.9 in /opt/anaconda3/lib/python3.12/site-packages (from folium) (3.1.4)
Requirement already satisfied: numpy in /opt/anaconda3/lib/python3.12/site-packages (from folium) (1.26.4)
Requirement already satisfied: requests in /opt/anaconda3/lib/python3.12/site-packages (from folium) (2.32.2)
Requirement already satisfied: xyzservices in /opt/anaconda3/lib/python3.12/site-packages (from folium) (2022.9.0)
Requirement already satisfied: MarkupSafe>=2.0 in /opt/anaconda3/lib/python3.12/site-packages (from jinja2>=2.9->folium) (2.1.3)
Requirement already satisfied: charset-normalizer<4,>=2 in /opt/anaconda3/lib/python3.12/site-packages (from requests->folium) (2.0.4)
Requirement already satisfied: idna<4,>=2.5 in /opt/anaconda3/lib/python3.12/site-packages (from requests->folium) (3.7)
Requirement already satisfied: urllib3<3,>=1.21.1 in /opt/anaconda3/lib/python3.12/site-packages (from requests->folium) (2.2.2)
Requirement already satisfied: certifi>=2017.4.17 in /opt/anaconda3/lib/python3.12/site-packages (from requests->folium) (2024.8.30)
libraries installed!

df = pd.read_csv('KCPD_Crime_Data_2024_20241201.csv')

#The default max column output is limited and this snippet allows me to render every column when a dataframe is called.
pd.options.display.max_columns = None

#Ensure the dataset imported correctly.
df.head()

print(df.info())

print(df.isnull().sum())

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 95932 entries, 0 to 95931
Data columns (total 24 columns):
 #   Column              Non-Null Count  Dtype  
---  ------              --------------  -----  
 0   Report_No           95932 non-null  object 
 1   Reported_Date       95932 non-null  object 
 2   Reported_Time       95932 non-null  object 
 3   From_Date           95932 non-null  object 
 4   From_Time           95932 non-null  object 
 5   To_Date             31503 non-null  object 
 6   To_Time             31503 non-null  object 
 7   Offense             95932 non-null  object 
 8   IBRS                87350 non-null  object 
 9   Description         87350 non-null  object 
 10  Beat                95926 non-null  float64
 11  Address             95932 non-null  object 
 12  City                95932 non-null  object 
 13  Zip Code            91243 non-null  float64
 14  Rep_Dist            86051 non-null  object 
 15  Area                95929 non-null  object 
 16  DVFlag              95932 non-null  bool   
 17  Involvement         95932 non-null  object 
 18  Race                83724 non-null  object 
 19  Sex                 84772 non-null  object 
 20  Age                 69651 non-null  float64
 21  Fire Arm Used Flag  95932 non-null  bool   
 22  Location            93795 non-null  object 
 23  Age_Range           69651 non-null  object 
dtypes: bool(2), float64(3), object(19)
memory usage: 16.3+ MB
None
Report_No                 0
Reported_Date             0
Reported_Time             0
From_Date                 0
From_Time                 0
To_Date               64429
To_Time               64429
Offense                   0
IBRS                   8582
Description            8582
Beat                      6
Address                   0
City                      0
Zip Code               4689
Rep_Dist               9881
Area                      3
DVFlag                    0
Involvement               0
Race                  12208
Sex                   11160
Age                   26281
Fire Arm Used Flag        0
Location               2137
Age_Range             26281
dtype: int64

#Ensure the dates are in datetime format for accurate temporal analysis.
df['Reported_Date'] = pd.to_datetime(df['Reported_Date'])
df['From_Date'] = pd.to_datetime(df['From_Date'])

#Getting rid of the colons to simplify timedata conversion.
df[['Reported_Time', 'From_Time']] = df[['Reported_Time', 'From_Time']].replace(':', '', regex=True)

#Convert integer to string with leading zeros and format to HH:MM
df['Reported_Time'] = df['Reported_Time'].apply(lambda x: f"{int(x):04d}")  #Ensure 4-digit format
df['From_Time'] = df['From_Time'].apply(lambda x: f"{int(x):04d}")  #Ensure 4-digit format
df['Reported_Time'] = pd.to_datetime(df['Reported_Time'], format='%H%M').dt.time
df['From_Time'] = pd.to_datetime(df['From_Time'], format='%H%M').dt.time

df.head(1)

df[['To_Date','To_Time']].isnull().sum()

To_Date    64429
To_Time    64429
dtype: int64

#Keeping the values in timedate and maintaining integrity. Replacing the null values can be filtered out for analysis accuracy.
df['To_Time'] = df['To_Time'].fillna('00:00:00')

df['To_Date'] = pd.to_datetime(df['To_Date'])

df['To_Time'] = df['To_Time'].replace(':', '', regex=True)

#Convert integer to string with leading zeros and format to HH:MM
df['To_Time'] = df['To_Time'].apply(lambda x: f"{int(x):04d}")  #Ensure 4-digit format
df['To_Time'] = pd.to_datetime(df['To_Time'], format='%H%M').dt.time

 # Replace nulls in To_Date with a placeholder date
df['To_Date'] = df['To_Date'].fillna(pd.Timestamp('2222-01-01'))

df.isnull().sum()

Report_No                 0
Reported_Date             0
Reported_Time             0
From_Date                 0
From_Time                 0
To_Date                   0
To_Time                   0
Offense                   0
IBRS                   8582
Description            8582
Beat                      6
Address                   0
City                      0
Zip Code               4689
Rep_Dist               9881
Area                      3
DVFlag                    0
Involvement               0
Race                  12208
Sex                   11160
Age                   26281
Fire Arm Used Flag        0
Location               2137
Age_Range             26281
dtype: int64

ibrs_with_nulls = df[df['IBRS'].isnull()]

ibrs_null_counts = ibrs_with_nulls.groupby('Offense')['IBRS'].size()
print(ibrs_null_counts) #Very difficult to discern why these values are missing.

Offense
Abuse of a Child                                                              13
Alcohol Influence Report                                                      23
Animal Bite                                                                   19
Assault (Aggravated)                                                          17
Assault (Aggravated) on Department Member/Outside Law Enforcement Officer      9
                                                                            ... 
Vehicular - Injury Hit and Run                                               154
Vehicular - Non-Injury                                                       522
Vehicular - Non-Injury Hit and Run                                           301
Violation of Ex-Parte Order of Protection                                     62
Violation of Full Order of Protection                                         79
Name: IBRS, Length: 100, dtype: int64

df['Rep_Dist'].value_counts()

Rep_Dist
PP0321    1758
PJ3601    1271
PJ4990     635
PC0323     557
PJ2650     476
          ... 
PJ2037       1
PJ4689       1
PJ7058       1
PJ6925       1
PJ5160       1
Name: count, Length: 6532, dtype: int64

rdist_with_nulls = df[df['Rep_Dist'].isnull()]

rdist_null_counts = rdist_with_nulls.groupby('Area')['Rep_Dist'].size()
print(rdist_null_counts)

Area
CPD     2642
EPD     1443
MPD     1898
NPD     1001
OSPD     420
SCP     1041
SPD     1436
Name: Rep_Dist, dtype: int64

#Replacing null values in the columns with "UNSPECIFIED" because it will have minimal effect on this analysis.
df[['IBRS','Description','Beat','Zip Code','Rep_Dist','Area','Location']] = df[['IBRS','Description','Beat','Zip Code','Rep_Dist','Area','Location']].fillna('UNSPECIFIED')

df.isnull().sum()

Report_No                 0
Reported_Date             0
Reported_Time             0
From_Date                 0
From_Time                 0
To_Date                   0
To_Time                   0
Offense                   0
IBRS                      0
Description               0
Beat                      0
Address                   0
City                      0
Zip Code                  0
Rep_Dist                  0
Area                      0
DVFlag                    0
Involvement               0
Race                  12208
Sex                   11160
Age                   26281
Fire Arm Used Flag        0
Location                  0
Age_Range             26281
dtype: int64

print(df['Race'].unique())
print(df['Sex'].unique())
print(df['Age'].unique())

[nan 'B' 'W' 'U' 'I']
[nan 'M' 'F' 'U']
[nan 19. 24. 56. 26. 45. 68. 42. 53. 61. 37. 36. 38. 20. 41. 30. 33. 66.
 47. 62. 25. 63. 28. 22. 46. 48. 70. 18. 31. 29. 32. 21. 51. 49. 60. 39.
 34. 40. 77. 27. 35. 55. 23. 43. 50. 76. 57. 44. 54. 64. 72. 52. 59. 58.
 71. 78. 69. 82. 65. 79. 73. 75. 67. 88. 85. 74. 81. 83. 87. 91. 86. 80.
 98. 90. 84. 93. 95. 92. 89. 94. 96. 99. 97.]

#'U' is already used to classify unknown variables. Using 0 as a placeholder allows me to maintain data integrity since a very large portion of the age column has null values.
df['Race'] = df['Race'].fillna('U')
df['Sex'] = df['Sex'].fillna('U')
df['Age'] = df['Age'].fillna(0)

print(df['Age_Range'].isnull().sum())

26281

#These are only null because the age was unknown.
df['Age_Range'] = df['Age_Range'].fillna('UNSPECIFIED')

df.isnull().sum()

Report_No             0
Reported_Date         0
Reported_Time         0
From_Date             0
From_Time             0
To_Date               0
To_Time               0
Offense               0
IBRS                  0
Description           0
Beat                  0
Address               0
City                  0
Zip Code              0
Rep_Dist              0
Area                  0
DVFlag                0
Involvement           0
Race                  0
Sex                   0
Age                   0
Fire Arm Used Flag    0
Location              0
Age_Range             0
dtype: int64

display(df['Location'])

0                               UNSPECIFIED
1                 POINT (-94.5856 39.06537)
2                               UNSPECIFIED
3        POINT (-94.572100389 39.280825631)
4                               UNSPECIFIED
                        ...                
95927            POINT (-94.54769 39.03518)
95928            POINT (-94.59937 39.00477)
95929            POINT (-94.58967 39.03483)
95930                           UNSPECIFIED
95931    POINT (-94.542065027 39.017103984)
Name: Location, Length: 95932, dtype: object

#Step 1: Handle "UNSPECIFIED" and keep those rows as NaN in new columns. Having strings in these column will be problematic for Pandas functions.
df['Lat_Lon'] = df['Location'].where(~df['Location'].str.contains('UNSPECIFIED'), np.nan)

#Step 2: Remove the word "POINT" and parentheses for valid rows
df['Lat_Lon'] = df['Lat_Lon'].str.replace('POINT ', '', regex=False).str.strip('()')

#Step 3: Split into Latitude and Longitude
df[['Longitude', 'Latitude']] = df['Lat_Lon'].str.split(' ', expand=True)

#Step 4: Convert Latitude and Longitude to floats
df['Longitude'] = pd.to_numeric(df['Longitude'], errors='coerce')
df['Latitude'] = pd.to_numeric(df['Latitude'], errors='coerce')

#Step 5: Drop the 'Lat_Lon' column
df = df.drop(columns=['Lat_Lon'])

display(df.head())

#Filter out the rows with null coordinates
geo_data = df.dropna(subset=['Latitude', 'Longitude'])
geo_data['Latitude'] = pd.to_numeric(geo_data['Latitude'], errors='coerce')
geo_data['Longitude'] = pd.to_numeric(geo_data['Longitude'], errors='coerce')

#Create a map centered around Kansas City, MO
center_lat = geo_data['Latitude'].mean()
center_lon = geo_data['Longitude'].mean()
crime_map = folium.Map(location=[center_lat, center_lon], zoom_start=11)

#Create the data for the heatmaps
heatmap_data = geo_data[['Latitude', 'Longitude']].values.tolist()

HeatMap(heatmap_data, radius=8).add_to(crime_map)

crime_map.save('crime_heatmap.html')

crime_map

# Group by 'Area' to find top hotspots
hotspots = geo_data.groupby('Area').size().sort_values(ascending=False)

print("Hotspots by Incident Count:")
print(hotspots)

#Add markers for the top hotspots
for area, count in hotspots.items():
    #Get the mean coordinates for each area
    coords = geo_data[geo_data['Area'] == area][['Latitude', 'Longitude']].mean()
    
    #Add marker to the map
    folium.Marker(
        location=[coords['Latitude'], coords['Longitude']],
        popup=f"Area: {area}<br>Incidents: {count}",
        icon=folium.Icon(color='red', icon='info-sign')
    ).add_to(crime_map)

#Add layer control for visibilty enhancement
folium.LayerControl().add_to(crime_map)

crime_map.save('crime_hotspots_map.html')

crime_map

Hotspots by Incident Count:
Area
CPD            27471
EPD            21862
MPD            18554
SPD             9419
NPD             8747
SCP             7396
OSPD             343
UNSPECIFIED        3
dtype: int64

#Create a base map
crime_map = folium.Map(location=[39.0997, -94.5786], zoom_start=11)

#Loop through each area and create a separate heatmap layer
for area, group in geo_data.groupby('Area'):
    #Skip if there's no location data
    if group[['Latitude', 'Longitude']].isnull().any(axis=None):
        continue
        
    #FeatureGroup
    area_group = folium.FeatureGroup(name=f"Area: {area}")
    
    #Add a heatmap to the FeatureGroup
    HeatMap(
        group[['Latitude', 'Longitude']].dropna().values.tolist(),
        radius=10, blur=12, min_opacity=0.4
    ).add_to(area_group)
    
    # Add the FeatureGroup to the map
    crime_map.add_child(area_group)

#Add LayerControl for toggling areas
folium.LayerControl().add_to(crime_map)

crime_map.save('layered_heatmap_by_area.html')

display(crime_map)

#Plot the data in a bargraph to see the numbers
division_counts = df['Area'].value_counts()

fig = px.bar(
    x=division_counts.index,
    y=division_counts.values,
    color=division_counts.index,
    labels={'x': 'Patrol Division', 'y': 'Number of Incidents'},
    title='Crime Incidents by Patrol Division',
    text=division_counts.values
)

fig.update_traces(
    textposition='outside',
    textfont=dict(size=10, color='black')
)

fig.update_layout(
    xaxis_title="Patrol Division",
    yaxis_title="Number of Incidents",
    margin=dict(t=50, b=100),
    xaxis=dict(tickangle=-45)
)

fig.show()

gradients = {
    'M': {0.4: 'steelblue', 0.7: 'blue', 1: 'darkblue'},  # Male: Blue gradient
    'F': {0.4: 'pink', 0.7: 'hotpink', 1: 'deeppink'}     # Female: Pink gradient
}

gender_map = folium.Map(location=[39.0997, -94.5786], zoom_start=11)

#Add heatmaps for both genders on the same map
for gender in ['M', 'F']:
    gender_data = df[df['Sex'] == gender][['Latitude', 'Longitude']].dropna()
    
    #Skip if no valid data
    if gender_data.empty:
        print(f"No data available for gender: {gender}")
        continue
    
    #Add heatmap directly to the map
    HeatMap(
        gender_data.values.tolist(),
        radius=12,
        blur=15,
        gradient=gradients[gender],
        min_opacity=0.5,
    ).add_to(gender_map)
#LayerControl
folium.LayerControl().add_to(gender_map)

gender_map.save('combined_gender_heatmap.html')

display(gender_map)

#Calculate counts for each gender
gender_counts = df['Sex'].value_counts()

fig = px.bar(
    x=gender_counts.index,
    y=gender_counts.values,
    color=gender_counts.index,
    labels={'x': 'Gender', 'y': 'Number of Incidents'},
    title='Crime Incidents by Gender',
    text=gender_counts.values
)

fig.update_traces(
    textposition='outside',
    textfont=dict(size=12, color='black') 
)

fig.update_layout(
    xaxis_title="Gender",
    yaxis_title="Number of Incidents",
    margin=dict(t=50, b=100),
    xaxis=dict(tickangle=0)
)

fig.show()

#No 'Unspecified' allowed
filtered_data = df[df['Description'] != 'UNSPECIFIED']

#Find the top 5 crimes
top_5_crimes = filtered_data['Description'].value_counts().head(5).index

#Filter location data for top 5 crimes
top_5_data = df[df['Description'].isin(top_5_crimes)][['Latitude', 'Longitude', 'Description']].dropna()

#Colors for each crime
gradients = {
    'Simple Assault': {0.4: 'lightblue', 0.7: 'blue', 1: 'darkblue'},
    'Motor Vehicle Theft': {0.4: 'lightgreen', 0.7: 'green', 1: 'darkgreen'},
    'Vandalism/Destruction of Property': {0.4: 'lightcoral', 0.7: 'red', 1: 'darkred'},
    'Aggravated Assault': {0.4: 'khaki', 0.7: 'gold', 1: 'darkgoldenrod'},
    'Shoplifting': {0.4: 'plum', 0.7: 'purple', 1: 'darkviolet'},
}

#Create the base map
crimes_map = folium.Map(location=[39.0997, -94.5786], zoom_start=11)

#Add a heatmap for each crime
for crime in top_5_crimes:
    crimes_data = top_5_data[top_5_data['Description'] == crime][['Latitude', 'Longitude']]
    
    if crimes_data.empty:
        continue
    
    HeatMap(
        crimes_data.values.tolist(),
        radius=10,
        blur=8,
        min_opacity=0.3,
        gradient=gradients.get(crime, {0.4: 'lightblue', 0.65: 'blue', 1: 'darkblue'}),
        name=crime
    ).add_to(crimes_map)

folium.LayerControl().add_to(crimes_map)

crimes_map.save('top_5_crimes_heatmap.html')

display(crimes_map)

#Calculate the counts for the top 5 crimes
top_5_crime_counts = df[df['Description'].isin(top_5_crimes)]['Description'].value_counts()

fig = px.bar(
    x=top_5_crime_counts.index,
    y=top_5_crime_counts.values,
    color=top_5_crime_counts.index,
    labels={'x': 'Crime Type', 'y': 'Number of Incidents'},
    title='Top 5 Crimes by Frequency',
    text=top_5_crime_counts.values
)

fig.update_traces(
    textposition='outside',
    textfont=dict(size=12, color='black') 
)

fig.update_layout(
    xaxis_title="Crime Type",
    yaxis_title="Number of Incidents",
    margin=dict(t=50, b=100),
    xaxis=dict(tickangle=-45)  
)

fig.show()

#Filter data where DVFlag is True
dv_data = geo_data[geo_data['DVFlag'] == True]

dv_data = dv_data.dropna(subset=['Latitude', 'Longitude'])

dv_map = folium.Map(location=[39.0997, -94.5786], zoom_start=11)

heatmap_data = dv_data[['Latitude', 'Longitude']].dropna().values.tolist()

#Add a heatmap for domestic violence incidents
HeatMap(
    heatmap_data,
    radius=10, blur=12, min_opacity=0.4
).add_to(dv_map)

dv_map.save('dv_flag_heatmap.html')

dv_map

dvflag_counts = df['DVFlag'].value_counts()

custom_labels = {True: 'Domestic Violence', False: 'Non-Domestic Violence'}

fig = px.bar(
    x=[custom_labels[val] for val in dvflag_counts.index],
    y=dvflag_counts.values,
    color=[custom_labels[val] for val in dvflag_counts.index],
    labels={'x': 'Incident Type', 'y': 'Number of Incidents'},
    title='Incidents by DVFlag',
    text=dvflag_counts.values  
)

fig.update_traces(
    textposition='outside', 
    textfont=dict(size=12, color='black') 
)

fig.update_layout(
    xaxis_title="Incident Type",
    yaxis_title="Number of Incidents",
    margin=dict(t=50, b=100),
    xaxis=dict(tickangle=0) 
)

fig.show()

map_center = [geo_data['Latitude'].mean(), geo_data['Longitude'].mean()]
division_streets_map = folium.Map(location=map_center, zoom_start=11)

#Step 1: Extract the street name by removing numbers and spaces before the first string character
geo_data['Street'] = geo_data['Address'].str.replace(r'^\d+\s*', '', regex=True)

#Step 2: Filter out rows with "UNSPECIFIED" in the Street or Area column
geo_data = geo_data[~geo_data['Street'].str.contains("UNSPECIFIED", na=False)]
geo_data = geo_data[~geo_data['Area'].str.contains("UNSPECIFIED", na=False)]

#Step 3: Ensure no null values exist in required columns
geo_data = geo_data.dropna(subset=['Area', 'Latitude', 'Longitude'])

#Step 4: Group by 'Area' and 'Street' to find incident counts
area_street_hotspots = (
    geo_data.groupby(['Area', 'Street'])
    .size()
    .reset_index(name='Incident Count')
    .sort_values(by=['Area', 'Incident Count'], ascending=[True, False])
)

#Step 5: Get the top 5 streets per area
top_street_per_area = (
    area_street_hotspots.groupby('Area', group_keys=False)
    .apply(lambda x: x.head(5))
    .reset_index(drop=True)
)

#Add a heatmap layer for each Area's top 5 streets
for area in top_street_per_area['Area'].unique():
    area_data = geo_data[geo_data['Area'] == area]
    top_streets = top_street_per_area[top_street_per_area['Area'] == area]['Street']
    area_data = area_data[area_data['Street'].isin(top_streets)]
    
    heatmap_layer = HeatMap(area_data[['Latitude', 'Longitude']].dropna().values, name=f"Hotspots in {area}")
    division_streets_map.add_child(heatmap_layer)

folium.LayerControl().add_to(division_streets_map)
division_streets_map.save('hotspot_map.html')

division_streets_map

#I could not figure out how to debug the plotly loop for this so I switched to subplots
#Find the unique areas
unique_areas = top_street_per_area['Area'].unique()

#Set up the subplot grid
num_areas = len(unique_areas)
fig, axes = plt.subplots(num_areas, 1, figsize=(10, 6.5 * num_areas), constrained_layout=True)

colors = plt.cm.tab20(np.linspace(0, 1, 10)) 

#Create a bar chart for each area
for i, area in enumerate(unique_areas):
    ax = axes[i] if num_areas > 1 else axes 
    area_data = top_street_per_area[top_street_per_area['Area'] == area]

    bars = ax.bar(
        area_data['Street'],
        area_data['Incident Count'],
        color=colors[:len(area_data)],
        edgecolor='black'
    )

    for bar in bars:
        height = bar.get_height()
        ax.annotate(
            f"{height}",
            xy=(bar.get_x() + bar.get_width() / 2, height),
            xytext=(0, 5),
            textcoords="offset points",
            ha='center',
            va='bottom',
            fontsize=10,
            color='black',
            weight='bold'
        )
    
    ax.set_title(f"Top 5 Streets in {area}", fontsize=14)
    ax.set_xlabel("Street", fontsize=12)
    ax.set_ylabel("Incident Count", fontsize=12)
    ax.set_xticks(range(len(area_data['Street'])))
    ax.set_xticklabels(area_data['Street'], rotation=45, ha='right')

plt.show()

Introduction¶

About the Data: Kansas City Police Department (KCPD) Crime Data¶

Columns and Descriptions¶

IMPORTING LIBRARIES AND DATA¶

DATA PRE-PROCESSING¶

GEOSPATIAL ANALYSIS¶

Crime Heatmap¶

Observations:¶

Crime Hotspot Map (with Markers)¶

Observations:¶

Layered Heatmaps by Area¶

Observations:¶

Combined Gender-Specific Heatmaps¶

Observations:¶

Top 5 Crimes Heatmap¶

Observations:¶

Domestic Violence Heatmap¶

Observations:¶

Hotspot Map by Streets¶

Observations:¶

CONCLUSION AND FINAL THOUGHTS¶

Implications:¶

Future Directions:¶

Final Thoughts¶

	Report_No	Reported_Date	Reported_Time	From_Date	From_Time	To_Date	To_Time	Offense	IBRS	Description	Beat	Address	City	Zip Code	Rep_Dist	Area	DVFlag	Involvement	Race	Sex	Age	Fire Arm Used Flag	Location	Age_Range
0	KC24000270	01/02/2024	04:53	01/02/2024	04:53	NaN	NaN	Trespass of Real Property	90J	Trespass of Real Property	113.0	1200 MAIN ST	KANSAS CITY	64106.0	PJ1087	CPD	False	VIC	NaN	NaN	NaN	False	NaN	NaN
1	KC24000567	01/03/2024	16:30	12/31/2023	16:30	NaN	NaN	Stealing from Building/Residence	23H	All Other Larceny	132.0	3400 MAIN ST	KANSAS CITY	64111.0	PJ2753	CPD	False	VIC	NaN	NaN	NaN	False	POINT (-94.5856 39.06537)	NaN
2	KC24000877	01/04/2024	15:15	01/04/2024	15:15	NaN	NaN	Vehicular - Non-Injury Hit and Run	NaN	NaN	123.0	W I 670 HWY and W I 70 HWY	KANSAS CITY	NaN	NaN	CPD	False	SUS	B	M	19.0	False	NaN	18-24
3	KC24001196	01/06/2024	00:48	01/06/2024	00:48	NaN	NaN	Stolen Auto	240	Motor Vehicle Theft	642.0	10300 N CHERRY DR	KANSAS CITY	NaN	NaN	SCP	False	CMP VIC	W	M	24.0	False	POINT (-94.572100389 39.280825631)	18-24
4	KC24001447	01/07/2024	07:00	01/07/2024	07:00	NaN	NaN	Assault (Aggravated)	26C	Impersonation	115.0	00 W PERSHING RD	KANSAS CITY	64108.0	PJ1831	CPD	False	VIC OTH	W	M	56.0	False	NaN	55-64

	Report_No	Reported_Date	Reported_Time	From_Date	From_Time	To_Date	To_Time	Offense	IBRS	Description	Beat	Address	City	Zip Code	Rep_Dist	Area	DVFlag	Involvement	Race	Sex	Age	Fire Arm Used Flag	Location	Age_Range	Longitude	Latitude
0	KC24000270	2024-01-02	04:53:00	2024-01-02	04:53:00	2222-01-01	00:00:00	Trespass of Real Property	90J	Trespass of Real Property	113.0	1200 MAIN ST	KANSAS CITY	64106.0	PJ1087	CPD	False	VIC	U	U	0.0	False	UNSPECIFIED	UNSPECIFIED	NaN	NaN
1	KC24000567	2024-01-03	16:30:00	2023-12-31	16:30:00	2222-01-01	00:00:00	Stealing from Building/Residence	23H	All Other Larceny	132.0	3400 MAIN ST	KANSAS CITY	64111.0	PJ2753	CPD	False	VIC	U	U	0.0	False	POINT (-94.5856 39.06537)	UNSPECIFIED	-94.5856	39.065370
2	KC24000877	2024-01-04	15:15:00	2024-01-04	15:15:00	2222-01-01	00:00:00	Vehicular - Non-Injury Hit and Run	UNSPECIFIED	UNSPECIFIED	123.0	W I 670 HWY and W I 70 HWY	KANSAS CITY	UNSPECIFIED	UNSPECIFIED	CPD	False	SUS	B	M	19.0	False	UNSPECIFIED	18-24	NaN	NaN
3	KC24001196	2024-01-06	00:48:00	2024-01-06	00:48:00	2222-01-01	00:00:00	Stolen Auto	240	Motor Vehicle Theft	642.0	10300 N CHERRY DR	KANSAS CITY	UNSPECIFIED	UNSPECIFIED	SCP	False	CMP VIC	W	M	24.0	False	POINT (-94.572100389 39.280825631)	18-24	-94.5721	39.280826
4	KC24001447	2024-01-07	07:00:00	2024-01-07	07:00:00	2222-01-01	00:00:00	Assault (Aggravated)	26C	Impersonation	115.0	00 W PERSHING RD	KANSAS CITY	64108.0	PJ1831	CPD	False	VIC OTH	W	M	56.0	False	UNSPECIFIED	55-64	NaN	NaN